fullstack-developer

fullstack-developer is a skill for Claude Code, Codex from medy-gribkov/arcana. It costs 0 tokens per session (1,700 once invoked), scanned A, original, Apache-2.0.

Full-stack web development guidance covering React interfaces, Node.js servers, databases, and application architecture. It emphasizes typed code, input validation, consistent errors, and separating different parts of an application.

In plain words
What is it for?
Use it to build frontends, APIs, database-backed applications, and deployments involving technologies such as React, Next.js, Express, REST, GraphQL, MongoDB, or PostgreSQL.
Why use it?
It helps prevent common problems such as accepting invalid request data, returning inconsistent errors, or mixing unrelated responsibilities. It gives a repeatable structure for building web features end to end.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to build frontends, APIs, database-backed applications, and deployments involving technologies such as React, Next.js, Express, REST, GraphQL, MongoDB, or PostgreSQL.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/medy-gribkov/arcana/fullstack-developer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add medy-gribkov/arcana --skill fullstack-developer
Clone the repo
git clone --depth 1 https://github.com/medy-gribkov/arcana

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin fullstack-developer — /plugin install fullstack-developer after adding the marketplace above.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fullstack-developer

README.md
[![agentmods](https://agentmods.dev/badge/skills/medy-gribkov/arcana/fullstack-developer/github.svg)](https://agentmods.dev/skills/medy-gribkov/arcana/fullstack-developer)
Your own site
<a href="https://agentmods.dev/skills/medy-gribkov/arcana/fullstack-developer"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/fullstack-developer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fullstack-developer

Your own site · 80×15
<a href="https://agentmods.dev/skills/medy-gribkov/arcana/fullstack-developer"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/fullstack-developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,700 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01700
Opus 5.5 $0.00000 $0.00680
Sonnet 5.5 $0.00000 $0.00340
Haiku 4.5 $0.00000 $0.00170

Measured 1mo ago against content hash 61f9b994b34f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fullstack-developer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/fullstack-developer/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full-Stack Developer

Act as a senior full-stack engineer. Write type-safe, production-ready code with proper error handling, validation, and separation of concerns.

API Design Workflow

Follow these steps when building any API endpoint.

  1. Define the route, HTTP method, and response shape first
  2. Create a Zod schema for request validation
  3. Implement the handler with typed request/response
  4. Add error handling that returns consistent JSON
  5. Write the corresponding client-side fetch hook

BAD: Unvalidated, untyped handler

// No validation, raw any types, inconsistent errors
app.post("/api/posts", async (req, res) => {
  const post = await db.post.create({ data: req.body });
  res.json(post);
});

GOOD: Validated, typed, consistent errors

import { z } from "zod";

const CreatePostSchema = z.object({
  title: z.string().min(1).max(200),
  content: z.string().min(1),
  published: z.boolean().default(false),
});

type CreatePostInput = z.infer<typeof CreatePostSchema>;

app.post("/api/posts", async (req: Request, res: Response) => {
  const result = CreatePostSchema.safeParse(req.body);
  if (!result.success) {
    return res.status(422).json({
      error: "Validation failed",
      details: result.error.flatten().fieldErrors,
    });
  }

  const post = await prisma.post.create({ data: result.data });
  return res.status(201).json({ data: post });
});

Error Response Shape

Every error response must follow this structure:

interface ApiError {
  error: string;
  code?: string;
  details?: Record<string, string[]>;
}

Map status codes consistently:

  • 201 after successful creation
  • 204 after successful deletion (no body)
  • 400 malformed request, 422 valid JSON but failed validation
  • 401 missing auth, 403 insufficient permissions
  • 409 conflict (duplicate unique field)
  • 429 rate limited

React Component Patterns

Follow these steps when building any component.

  1. Define the props interface with explicit types
  2. Handle all states: loading, error, empty, success
  3. Extract data fetching into custom hooks
  4. Keep components under 80 lines. Split if larger
  5. Co-locate types, hooks, and tests with the component

Read the full file on GitHub · 241 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 241 lines · 0 tokens per session scan A 61f9b994b34f

Subscribe to this mod's changes

fullstack-developer is a skill published in the GitHub repository medy-gribkov/arcana (1 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,700 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.